A New Segmentation Approach in Structured Self-Organizing Maps for Image Retrieval

Content-based image retrieval (CBIR) is the problem of searching for digital images in large databases. In order to search and index the images, different models of Self-organizing Maps (SOM), such as the Tree-Structured self labeled self-organizing maps (TS-SL-SOM), were used because combines features of data, quantization and topology preservation with good results. TS-SL-SOM has a dynamic and data-driven tree topology with maps as nodes. From top to down, maps are segmented and each labeled region generates a new child map in the next level. For image retrieval, the feature vectors of images were mapped into the TS-SL-SOM neural network. Although it has presented good results when applied for indexing images, in comparison with other structures. In this paper a new SOM segmentation is proposed for improving the results in CBIR. The proposed algorithm is based in the well known idea that in the edges of segments the activation of neurons is less than in the center of segments. Better retrieval results were accomplished when using the proposed method in comparison with the traditional method.